Beginning with epoch 1,loss is equal to 0

[goldcarpenter]

Your examples/notebook's work is wonderful.thank you.
Now, I hope to use our dataset. It ran well ,but loss was too small.Like this,
Train epoch: 0 [0/512] Avg. Loss: 0.701 Avg. Time: 1.706 INFO:__main__: Train epoch: 0 [10/512] Avg. Loss: 0.589 Avg. Time: 0.434 INFO:__main__: Train epoch: 0 [20/512] Avg. Loss: 0.407 Avg. Time: 0.374
Finally,we got nothing except red in predict result.
our dataset is medical image, gt is white(255).we set NUM_CLASSES = 2.Is that right?

[DrSleep]

closing since this is not related to the code released here.

[kingyj7]

Hi, @goldcarpenter , I also encounter this problem! When I set NUM_CLASSES = 2 for my own data to classify foreground and background, the loss down to 0 quickly. And after 5 epochs, i got mIOU=1 for all validation images! If you have solved this problem, please let me know, Thank you~